© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16508
    Prev
    Next
    INDEX
    Explanations

    online videos

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fort
    -0.74
     flush
    -0.69
     malaria
    -0.65
     betray
    -0.64
     places
    -0.63
     construct
    -0.63
     levy
    -0.63
     mal
    -0.62
     increment
    -0.62
     moth
    -0.61
    POSITIVE LOGITS
    Video
    3.92
    video
    2.52
    VIDEO
    2.32
     Video
    2.27
     VIDEO
    1.99
     Videos
    1.89
     video
    1.85
    videos
    1.83
    Audio
    1.71
    ideos
    1.62
    Activations Density 0.012%

    No Known Activations